Weighted Vector Addition on Nvidia Cuda framework
​(2014)
High Level Overview of the code to follow (heterogeneous programming)
  1. Prepare memory by copying data from the CPU memory to the GPU memory
  2. Run the GPU code (kernel) on the GPU until it completes
  3. Copy back over the results to CPU memory

Functionally Equivalent Code for CPU only Execution

Kernel And Implementation for GPU Execution